Hi, OFED 1.5.3-rc4 is available Notes:
The tarball is available on: http://www.openfabrics.org/downloads/OFED/ofed-1.5.3/OFED-1.5.3-rc4.tgz To get BUILD_ID run ofed_info Please report any issues in bugzilla https://bugs.openfabrics.org/ for OFED 1.5.3 Vladimir & Tziporet ======================================================================== Supported Platforms and Operating Systems --------------------------------------------- o CPU architectures: - x86_64 - x86 - ppc64 - ia64 o Linux Operating Systems: - RedHat EL5 up4 2.6.18-164.el5 - RedHat EL5 up5 2.6.18-194.el5 - RedHat EL5 up6 2.6.18-238.el5 - RedHat EL6 2.6.32-71.el6 - SLES10 SP3 2.6.16.60-0.54-smp - SLES11 2.6.27.19-5-default - SLES11 SP1 2.6.32.12-0.7-default - Fedora Core12 2.6.31.5-127.fc12 * - OpenSuSE 11.2 2.6.31.5-0.1-default * - kernel.org 2.6.29 - 2.6.36 * * Minimal QA for these versions Main changes from 1.5.3-rc3: =========================== Updated packages: dapl-2.0.32
bug_id,"bug_severity","priority","op_sys","assigned_to","bug_status","resolution","short_desc" 2222,"major","P3","Other","[email protected]","CLOSED","FIXED","Compilation of OFA kernel fails after applying krping patch on 2.6.34" 2223,"blocker","P1","Other","[email protected]","RESOLVED","FIXED","Installation of OFED-1.5.3-rc2 fails on 2.6.35 kernel" 2229,"critical","P2","SLES 11","[email protected]","RESOLVED","FIXED","mmvapich2_gcc-1.6/mvapich2 option is not present while installing OFED on SLES platforms" 2236,"blocker","P5","RHEL 5","[email protected]","RESOLVED","FIXED","ofa-kernel build breaks on vanilla 2.6.33 and ppc64 due to missing kernel patch"
commit 936ed7828b82d5c0f0895da02bb9012b55363bd0 Merge: 71c5e46 35dbff5 Author: Vladimir Sokolovsky <[email protected]> Date: Mon Feb 14 15:05:51 2011 +0200 Merge branch 'ofed_kernel_1_5' of git://git.openfabrics.org/~mmarciniszyn/linux-2.6.to_ofed into ofed_kernel_1_5 commit 71c5e4653c76c0d0244c973a1387f3a5c5c715a3 Author: Nir Muchtar <[email protected]> Date: Mon Feb 14 10:13:19 2011 +0200 mlx4_en: Fix promiscuous mode issues Signed-off-by: Nir Muchtar <[email protected]> commit c0c255e3f783a1470de73bffa41d363a77edd300 Author: Vladimir Sokolovsky <[email protected]> Date: Sun Feb 13 10:13:02 2011 +0200 ppc64/backport: Add workaround for compilation on PPC64 with 2.6.[28-31] Signed-off-by: Vladimir Sokolovsky <[email protected]> commit 35dbff5c916967ec2fb0bec02c5ddd4ec7048d1a Author: Mike Marciniszyn <[email protected]> Date: Thu Feb 10 08:37:56 2011 -0500 IB/qib: Kernel BUG at include/linux/timer.h:82 The following panic BUG_ON occurs during qib testing: Kernel BUG at include/linux/timer.h:82 RIP [<ffffffff881f7109>] :ib_qib:start_timer+0x73/0x89 RSP <ffffffff80425bd0> <0>Kernel panic - not syncing: Fatal exception <0>Dumping qib trace buffer from panic qib_set_lid INFO: IB0:1 got a lid: 0xf8 Done dumping qib trace buffer BUG: warning at kernel/panic.c:137/panic() (Tainted: G The flaw is due to a missing state test when processing responses that results in an add_timer() call when the same timer is already queued. This code was executing in parallel with a QP destroy on another CPU that had changed the state to reset, but the missing test caused to response handling code to run on into the panic. Signed-off-by: Mike Marciniszyn <[email protected]> commit 767fcd6cd95d81ec524b265ab3a9ce02a279adc7 Author: [email protected] <[email protected]> Date: Wed Feb 9 16:47:00 2011 +0100 RDMA/code: Fix for problem with closing iWARP connection and DAPL Now DAPL and nes driver can close connection correctly. Corrections in AEQE handling were made. Signed-off-by: Mirek Walukiewicz <[email protected]> Signed-off-by: Faisal Latif <[email protected]> commit e4acba676b6ef0c5735fa5766ee998787742d704 Author: Vladimir Sokolovsky <[email protected]> Date: Wed Feb 9 18:22:49 2011 +0200 ppc64/backport: Add workaround for compilation on PPC64 with 2.6.3[3-6] Add an empty asm/iomap.h under kernel_addons for 2.6.3[3-6]* kernels BUG: http://bugs.openfabrics.org/bugzilla/show_bug.cgi?id=2236 Signed-off-by: Vladimir Sokolovsky <[email protected]> commit 815fbe8cd417b8eb3a399edbb7f5da4e50a1ede4 Author: Vladimir Sokolovsky <[email protected]> Date: Mon Feb 7 11:25:56 2011 +0200 Revert "openibd: Update script header" This reverts commit d477ac405deca4ee3e12d3dc67f3cf07178fb2c5. Reverted commit cause openibd service script to run after the network service script on RHEL5.x which affect bonding interface caonfiguration. Signed-off-by: Vladimir Sokolovsky <[email protected]> commit 98a3cc6b7569f96e46a15ac8190d1956bd869a56 Author: Nir Muchtar <[email protected]> Date: Sun Feb 6 17:38:16 2011 +0200 IB/core: Control number of retries for SA to leave an MCG Add a multicast leave maximum retry setting in sys/module/ib_sa/parameters/mcast_leave_retries. Add a debug print when the maximum retry count is reached. Signed-off-by: Nir Muchtar <[email protected]> Reviewed-by: Moni Shoua <[email protected]> commit 7aa40774dcf258def9c616bdf0465764210b06fa Author: Yossi Etigin <[email protected]> Date: Sun Feb 6 17:34:16 2011 +0200 IB/ipoib: Leave stale send-only multicast groups The kernel never leaves send only multicast groups. In addition, IPoIB doesn't implement real send only join but it sends the SM a send/receive join request. In order to avoid MC group explosion on the switch, a mechanism of garbage collection to unused multicast groups is required. Signed-off-by: Yossi Etigin <[email protected]> Signed-off-by: Moni Shoua <[email protected]> commit 6c01388c3b972814277372e5aee0e98b12f2d8c1 Author: Mike Marciniszyn <[email protected]> Date: Tue Feb 1 11:25:19 2011 -0500 IPoIB: fix faulty list maintenance in path and neigh list From: Gary Leshner <[email protected]> Added list_del to ipoib_mcast_free() and path_free() to remove the neigh from the path's neigh_list link list before freeing the memory it consumes. This makes the code consistent with ipoib_cm_handle_tx_wc() and other locations where the list_del() preceeds the call to ipoib_neigh_free(). Similarly, at list_del() now preceeds path_free() to remove the path from ipoib_dev_priv's path_list. Additionally, the fields neigh->ah and neigh->list were not being initialized upon allocation. The patch insures that these two remaining fields are initialized correctly. Signed-off-by: Mike Marciniszyn <[email protected]>
